scholarly journals Compositionality Decomposed: How do Neural Networks Generalise? (Extended Abstract)

2020 ◽  
Author(s):  
Dieuwke Hupkes ◽  
Verna Dankers ◽  
Mathijs Mul ◽  
Elia Bruni
Keyword(s):  
Neural Networks ◽  
Compositional Data ◽  
Empirical Studies ◽  
The Other ◽  
Philosophical Theory ◽  
Neural Models ◽  
Data Set ◽  
Vast Amount ◽  
Depth Analysis ◽  
The One

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally. As a response to this controversy, we present a set of tests that provide a bridge between, on the one hand, the vast amount of linguistic and philosophical theory about compositionality of language and, on the other, the successful neural models of language. We collect different interpretations of compositionality and translate them into five theoretically grounded tests for models that are formulated on a task-independent level. To demonstrate the usefulness of this evaluation paradigm, we instantiate these five tests on a highly compositional data set which we dub PCFG SET, apply the resulting tests to three popular sequence-to-sequence models and provide an in-depth analysis of the results.

scholarly journals Compositionality Decomposed: How do Neural Networks Generalise?

2020 ◽  
Vol 67 ◽  
pp. 757-795
Author(s):  
Dieuwke Hupkes ◽  
Verna Dankers ◽  
Mathijs Mul ◽  
Elia Bruni
Keyword(s):  
Neural Networks ◽  
Compositional Data ◽  
Empirical Studies ◽  
Neural Model ◽  
Training Data ◽  
Data Set ◽  
Depth Analysis ◽  
The One ◽  
Transformer Model ◽  
Composition Operations

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. As a response to this controversy, we present a set of tests that provide a bridge between, on the one hand, the vast amount of linguistic and philosophical theory about compositionality of language and, on the other, the successful neural models of language. We collect different interpretations of compositionality and translate them into five theoretically grounded tests for models that are formulated on a task-independent level. In particular, we provide tests to investigate (i) if models systematically recombine known parts and rules (ii) if models can extend their predictions beyond the length they have seen in the training data (iii) if models’ composition operations are local or global (iv) if models’ predictions are robust to synonym substitutions and (v) if models favour rules or exceptions during training. To demonstrate the usefulness of this evaluation paradigm, we instantiate these five tests on a highly compositional data set which we dub PCFG SET and apply the resulting tests to three popular sequence-to-sequence models: a recurrent, a convolution-based and a transformer model. We provide an in-depth analysis of the results, which uncover the strengths and weaknesses of these three architectures and point to potential areas of improvement.

An Introduction to Roman Retailing

2018 ◽  
Author(s):  
Steven J. R. Ellis
Keyword(s):  
The Other ◽  
Methodological Framework ◽  
Roman World ◽  
Depth Analysis ◽  
Food And Drink ◽  
The One ◽  
Value Of It

This chapter introduces the topic of retailing in the Roman world and outlines some of the important developments in its study. It establishes why the focus of the book zooms in from retailing in general to the retailing of food and drink in particular; thus from shops to bars. Another aim is to demonstrate the scope of the study, which is an in-depth analysis of specific shops and bars at Pompeii on the one hand, and on the other a broader survey of the retail landscapes of cities throughout the Roman world. Essentially this chapter provides the theoretical and methodological framework for the book, while also arguing for the value of it in the first place.

Dreams of Truck Drivers: A Test of the Continuity Hypothesis of Dreaming

2005 ◽  
Vol 25 (2) ◽  
pp. 179-186 ◽  
Author(s):  
Michael Schredl ◽  
Arthur Funkhouser ◽  
Nicole Arn
Keyword(s):  
Empirical Studies ◽  
Truck Drivers ◽  
The Other ◽  
Continuity Hypothesis ◽  
Future Studies ◽  
Daytime Activity ◽  
Close Relationship ◽  
The One ◽  
Dream Emotions ◽  
The Relationship

Empirical studies largely support the continuity hypothesis of dreaming. The present study investigated the frequency and emotional tone of dreams of truck drivers. On the one hand, the findings of the present study partly support the continuity regarding the time spent with driving/being in the truck and driving dreams and, on the other hand, a close relationship was found between daytime mood (feelings of stress, job satisfaction) and dream emotions, i.e., different dream characteristics were affected by different aspects of daytime activity. The results, thus, indicate that it is necessary to define very clearly how this continuity is to be conceptualized. The approach of formulating a mathematical model (cf. [1]) should be adopted in future studies in order to specify the factors and their magnitude in the relationship between waking and dreaming.

Der Fall des Philosophen

2019 ◽  
Author(s):  
Hanna Gekle
Keyword(s):  
20Th Century ◽  
Oedipus Complex ◽  
The Other ◽  
Philosophical Theory ◽  
Ernst Bloch ◽  
The Uncanny ◽  
History Of ◽  
Painful Experience ◽  
The Moment ◽  
The One

The history of mental development on the one and the history of his writings on the other hand form the two separate but essentially intertwined strands of an archeology of Ernst Bloch´s thought undertaken in this book. Bloch as a philosopher is peculiar in that his initial access to thought rose from the depths of early, painful experience. To give expression to this experience, he not only needed to develop new categories, but first and foremost had to find words for it: the experience of the uncanny and the abysmal, of which he tells in Spuren, is on the level of philosophical theory juxtaposed by the “Dunkel des gerade gelebten Augenblicks” (darkness of the moment just lived) and his discovery of a “Noch-nicht-Bewusstes” (not-yet-conscious), thus metaphysically undermining the classical Oedipus complex in the succession of Freud. In this book, psyche, work and the history of the 20th century appear concentrated in Ernst Bloch the philosopher and contemporary witness, who paid tribute to these supra-individual powers in his work as much as he hoped to transgress them.

N. Belknap's Four-Valued Logic, Belknap Computer and New Proximity Functions for Comparing Discrete Objects

2021 ◽  
Vol 1 (2 (6)) ◽  
Author(s):  
Valerii Dmitrienko ◽  
Sergey Leonov ◽  
Mykola Mezentsev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
The Other ◽  
Proximity Function ◽  
Input Information ◽  
Proximity Measures ◽  
The One ◽  
True Values

The idea of ​​Belknap's four-valued logic is that modern computers should function normally not only with the true values ​​of the input information, but also under the conditions of inconsistency and incompleteness of true failures. Belknap's logic introduces four true values: T (true - true), F (false - false), N (none - nobody, nothing, none), B (both - the two, not only the one but also the other).  For ease of work with these true values, the following designations are introduced: (1, 0, n, b). Belknap's logic can be used to obtain estimates of proximity measures for discrete objects, for which the functions Jaccard and Needhem, Russel and Rao, Sokal and Michener, Hamming, etc. are used. In this case, it becomes possible to assess the proximity, recognition and classification of objects in conditions of uncertainty when the true values ​​are taken from the set (1, 0, n, b). Based on the architecture of the Hamming neural network, neural networks have been developed that allow calculating the distances between objects described using true values ​​(1, 0, n, b). Keywords: four-valued Belknap logic, Belknap computer, proximity assessment, recognition and classification, proximity function, neural network.

scholarly journals There Is No Logical Negation Here, But There Are Alternatives: Modeling Conversational Negation with Distributional Semantics

2016 ◽  
Vol 42 (4) ◽  
pp. 637-660 ◽  
Author(s):  
Germán Kruszewski ◽  
Denis Paperno ◽  
Raffaella Bernardi ◽  
Marco Baroni
Keyword(s):  
Large Data ◽  
Semantic Space ◽  
The Other ◽  
Similarity Function ◽  
Distributional Semantics ◽  
Application Domain ◽  
Data Set ◽  
Logical Negation ◽  
The One ◽  
The Right

Logical negation is a challenge for distributional semantics, because predicates and their negations tend to occur in very similar contexts, and consequently their distributional vectors are very similar. Indeed, it is not even clear what properties a “negated” distributional vector should possess. However, when linguistic negation is considered in its actual discourse usage, it often performs a role that is quite different from straightforward logical negation. If someone states, in the middle of a conversation, that “This is not a dog,” the negation strongly suggests a restricted set of alternative predicates that might hold true of the object being talked about. In particular, other canids and middle-sized mammals are plausible alternatives, birds are less likely, skyscrapers and other large buildings virtually impossible. Conversational negation acts like a graded similarity function, of the sort that distributional semantics might be good at capturing. In this article, we introduce a large data set of alternative plausibility ratings for conversationally negated nominal predicates, and we show that simple similarity in distributional semantic space provides an excellent fit to subject data. On the one hand, this fills a gap in the literature on conversational negation, proposing distributional semantics as the right tool to make explicit predictions about potential alternatives of negated predicates. On the other hand, the results suggest that negation, when addressed from a broader pragmatic perspective, far from being a nuisance, is an ideal application domain for distributional semantic methods.

Paternal Relationships With Sons and Daughters

2021 ◽  
pp. 331-354
Author(s):  
Lambrianos Nikiforidis
Keyword(s):  
Empirical Studies ◽  
The Other ◽  
Same Sex ◽  
Financial Decisions ◽  
Traditional Family ◽  
Biological Sex ◽  
The Family ◽  
The One ◽  
Parental Bias ◽  
Over Time

This chapter examines paternal relationships with sons and daughters. Identity drives investment (and parental investment in particular), because people invest in that which aligns with their identity. And biological sex drives identity. These two ideas combined imply that a parent-offspring match in biological sex can influence parental favoritism in a systematic manner, an idea supported by recent empirical studies. This parental bias of concordant-sex favoritism can have broad implications, outside the context of the traditional family structure. In single parent or same-sex parent households, the consequences of this bias can be even stronger, because there would not be an opposite-direction bias from the other parent to even things out. This favoritism could have even broader ramifications, entirely outside the context of the family. On the one hand, whenever social norms dictate that men should control a family’s financial decisions, then sons may systematically receive more resources than daughters. This asymmetry in investment would then result in ever-increasing advantages that persist over time. On the other hand, if women are a family’s primary shoppers, this can manifest in subtle but chronic favoritism for daughters.

Going Over: The Mesolithic-Neolithic Transition in North-West Europe

2007 ◽  
Keyword(s):  
The Other ◽  
Way Of Life ◽  
Northern Spain ◽  
Hunter Gatherers ◽  
Data Set ◽  
North West ◽  
Southern Scandinavia ◽  
The One ◽  
Early Farmers ◽  
Rich Data

The processes involved in the transformation of society from Mesolithic hunter-gatherers to Neolithic farmers were complex. They involved changes not only in subsistence but also in how people thought about themselves and their worlds, from their pasts to their animals. Two sets of protagonists have often been lined up in the long-running debates about these processes: on the one hand incoming farmers and on the other indigenous hunter-gatherers. Both have found advocates as the dominant force in the transitions to a new way of life. North-west Europe presents a very rich data set for this fundamental change, and research has both extended and deepened our knowledge of regional sequences, from the sixth to the fourth millennia bc. One of the most striking results is the evident diversity from northern Spain to southern Scandinavia. No one region is quite like another; hunter-gatherers and early farmers alike were also varied and the old labels of Mesolithic and Neolithic are increasingly inadequate to capture the diversity of human agency and belief. Surveys of the most recent evidence presented here also strongly suggest a diversity of transformations. Some cases of colonization on the one hand and indigenous adoption on the other can still be argued, but many situations now seem to involve complex fusions and mixtures. This wide-ranging set of papers offers an overview of this fundamental transition.

Impossible Languages

2016 ◽  
Author(s):  
Andrea Moro
Keyword(s):  
Neural Networks ◽  
Laws Of Nature ◽  
The Other ◽  
Human Language ◽  
Finite Set ◽  
The One ◽  
Physical Laws ◽  
Flow Of Information ◽  
Novel Structures

Understanding the nature and the structure of human language coincides with capturing the constraints which make a conceivable language possible or, equivalently, with discovering whether there can be any impossible languages at all. This book explores these related issues, paralleling the effort of a biologist who attempts at describing the class of impossible animals. In biology, one can appeal for example to physical laws of nature (such as entropy or gravity) but when it comes to language the path becomes intricate and difficult for the physical laws cannot be exploited. In linguistics, in fact, there are two distinct empirical domains to explore: on the one hand, the formal domain of syntax, where different languages are compared trying to understand how much they can differ; on the other, the neurobiological domain, where the flow of information through the complex neural networks and the electric code exploited by neurons is uncovered and measured. By referring to the most advanced experiments in Neurolinguistics the book in fact offers an updated descriptions of modern linguistics and allows the reader to formulate new and surprising questions. Moreover, since syntax - the capacity to generate novel structures (sentences) by recombining a finite set of elements (words) - is the fingerprint of all and only human languages this books ultimately deals with the fundamental questions which characterize the search for our origins.

scholarly journals Frédéric Chopin, entre exacerbation romantique du modèle vocal et innovations percussives : une mixité dynamique

2021 ◽  
pp. 107-123
Author(s):  
Martin Laliberté
Keyword(s):  
The Other ◽  
Frederic Chopin ◽  
Western Music ◽  
Other Hand ◽  
Depth Analysis ◽  
Percussion Instrument ◽  
The One ◽  
Mixed Status

After some in-depth analysis, for instance, of the first Ballade in G minor (1836), Frédéric Chopin’s music reveals itself as a striking case of a musical equilibrium between two major musical tendencies. On the one hand, his music brings the reaching towards an idealised voice to a full and very convincing development. His musical themes sing most of the time while all the main characteristics of his writing explore continuous spaces, to the extent the piano can achieve. He uses many melodic chromaticisms and broad gestures, very voice-like phrasings ranging from the most delicate pianissimi to the extremely dramatic fortissimo, and other vocal features. On the other hand, his music is unavoidably written for a percussion instrument (the piano), makes much use of rhythms and often dances as well, while his accompaniments are thick with vertical features, accents and other percussive traits. In reality, Chopin’s music is in a striking state of equilibrium between the vocal and the percussive and constitutes a rich case of a mixed status between the two poles. Perhaps for one of the last times in Western music, Chopin is precisely at the point of equilibrium, before the rise of the percussive that gave birth to much of the twentieth century’s music. Chopin’s music will remain a true and much beloved monument of equilibrium.

Sign in / Sign up

Export Citation Format

Share Document